Model comparison
Gemini 1.0 Pro vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 27.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 0 categories and Tulu 3 (Tülu 3) 70B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.8 to 36.2.
- The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 42.7% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | |
| Noometry Index | 27.1 | 32.6 |
| Released | 2023-12-13 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 31.6 (#270), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1108 | 1236 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 16.4 (#292), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1220 |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 116.97 | — |
Math Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 8.7 (#315), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 4.4% |
| LMArena Math | 1132 | 1242 |
| MATH Level 5 | 11.2% | 42.7% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 15.5 (#286), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 34% | 46.3% |
| LMArena Expert | 1059 | — |
| MMLU | 70% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 33.5 (#247), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1138 | 1236 |
| LMArena Chinese | 1124 | 1249 |
| LMArena Russian | 1186 | 1246 |
| LMArena French | 1144 | — |
| LMArena German | 1125 | — |
| LMArena Japanese | 1023 | — |
| LMArena Spanish | 1118 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 57.9 (#262), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1233 |
Long Context Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 34.3 (#244), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1132 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Gemini 1.0 Pro: 36.2 (#259), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Gemini 1.0 Pro | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1149 | 1256 |
| LMArena Creative Writing | 1130 | 1231 |
| LMArena Multi-Turn | 1139 | 1252 |
Frequently asked questions
Is Gemini 1.0 Pro better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 27.1 on the Noometry Index.
Is Gemini 1.0 Pro or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 31.6 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.